> For the complete documentation index, see [llms.txt](https://docs.usepylon.com/pylon-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.usepylon.com/pylon-docs/getting-started/pylonboarding/knowledge-base.md).

# Knowledge Base

Create, manage, and surface help content for your customers, your team, and AI.

## Overview

Pylon’s Knowledge Base is designed to help you scale support, surface answers faster, and give both customers and internal teams the information they need—all in one place. Use it to:

* Document answers once and reuse them across workflows
* Enable customers to self-serve with accurate, searchable content
* Use [Copilot](/pylon-docs/knowledge-base/articles-and-collections/copilot.md) and [Missing Content](/pylon-docs/knowledge-base/missing-content.md) to AI draft content and identify common questions
* Build your support engine with [AI agents](/pylon-docs/agents/support-agent.md) reading from your knowledge base
* Centralize support, onboarding, and troubleshooting docs

***

## Setup

{% embed url="<https://demo.arcade.software/I3A4jC4giiysenSd8lk9?embed=&embed_desktop=inline&embed_mobile=tab&show_copy_link=true>" fullWidth="true" %}

***

## Use cases

* Public Help Center
  * Create a branded, SEO-optimized external knowledge base where users can search for help articles, FAQs, or onboarding content.
* Internal playbooks
  * Store escalation processes, troubleshooting guides, or policy documentation in internal-only articles your team can search.
* Generate articles with AI

  * Turn any issue resolution into a draft article with one click, then use AI to rewrite, summarize, or adjust tone before publishing.

  <div align="center" data-full-width="true"><figure><img src="https://982123570-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F9hXBoCTTNw5flARlUVJf%2Fuploads%2FsB7MAeX75wO4yecb8gFw%2FScreenshot%202025-05-20%20at%202.48.02%E2%80%AFPM.png?alt=media&amp;token=199fc90a-858e-493b-ab4f-8030928d8dac" alt="" width="375"><figcaption></figcaption></figure></div>
* Gated Customer Content
  * Share specific documentation with customers based on login or account metadata, like implementation guides for enterprise users.
* Power AI
  * Use your content to power AI features across the product, like a [Copilot](/pylon-docs/support-workflows/issues/copilot.md) for your team or [Ask AI](/pylon-docs/platform/ask-ai.md).

***

## Best practices

* Use visibility settings intentionally
  * Choose between Public, Customer, or Internal visibility for each article to match the desired audience, and turn on **Direct link only** to keep an article out of navigation and search.
  * Visibility doesn't control AI agents. Use **Support agent access** to choose which agents can read an article; internal articles are available to agents by default. See [Support agent access](/pylon-docs/knowledge-base/articles-and-collections.md#support-agent-access).

<div align="center"><figure><img src="https://982123570-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F9hXBoCTTNw5flARlUVJf%2Fuploads%2F223JXX1NL7cgaPfwdkGs%2FScreenshot%202025-05-20%20at%202.42.47%E2%80%AFPM.png?alt=media&amp;token=da24de7b-d312-49c3-b4ea-2c837dcd53c8" alt="" width="188"><figcaption></figcaption></figure></div>

* Organize with collections
  * Nest articles in logical groupings using Collections to help users find content faster.
* Standardize formatting with templates
  * Keep formatting clean and consistent using article templates. When generating an article with AI, the AI will follow your template.
* Link articles with relative links
  * Use relative links between articles to reduce the risk of broken links when reorganizing.
* Federated search
  * In [Resources](/pylon-docs/platform/training-data.md), connect your other documentation sources to get a federated [Search](/pylon-docs/knowledge-base/search.md) across all your data

***


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.usepylon.com/pylon-docs/getting-started/pylonboarding/knowledge-base.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.